{"id":"https://openalex.org/W7164857209","doi":"https://doi.org/10.1145/3805622.3810699","title":"Uncertainty-Gated Generative Compression for Structure-Preserving Multimedia Retrieval","display_name":"Uncertainty-Gated Generative Compression for Structure-Preserving Multimedia Retrieval","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164857209","doi":"https://doi.org/10.1145/3805622.3810699"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810699","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810699","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810699","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101524238","display_name":"Yiming Ding","orcid":"https://orcid.org/0000-0002-0990-735X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Ding","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-3967-3796","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071363709","display_name":"Z Q Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziang Chen","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-2833-2929","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027428789","display_name":"Jianguo Wei","orcid":"https://orcid.org/0000-0002-8964-9759"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Wei","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8964-9759","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93992472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1692","last_page":"1700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.325300008058548,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.325300008058548,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.21330000460147858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.08290000259876251,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.7013000249862671},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5756000280380249},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5278000235557556},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5102999806404114},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.49160000681877136},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.454800009727478},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077999949455261},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.7013000249862671},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5278000235557556},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.49160000681877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4058000147342682},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.3303000032901764},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C2778192920","wikidata":"https://www.wikidata.org/wiki/Q16874989","display_name":"Signal compression","level":4,"score":0.31679999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C64185310","wikidata":"https://www.wikidata.org/wiki/Q843483","display_name":"Rate\u2013distortion theory","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810699","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810699","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810699","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810699","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W1990457366","https://openalex.org/W2040903332","https://openalex.org/W2124509324","https://openalex.org/W2141362318","https://openalex.org/W2411707397","https://openalex.org/W2741137940","https://openalex.org/W2962687329","https://openalex.org/W2962785568","https://openalex.org/W2963154697","https://openalex.org/W2963372104","https://openalex.org/W2981613960","https://openalex.org/W3202918664","https://openalex.org/W4288083516","https://openalex.org/W4302023197","https://openalex.org/W4316830033","https://openalex.org/W4378771614","https://openalex.org/W4386065641","https://openalex.org/W4416048484","https://openalex.org/W6891791918","https://openalex.org/W6929482511"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"multimedia":[1],"retrieval":[2,31,153],"systems":[3],"increasingly":[4],"rely":[5],"on":[6,29,144],"compressed":[7],"visual":[8],"representations":[9],"for":[10],"storage":[11],"and":[12,26,117,146,161],"transmission":[13],"efficiency.":[14],"However,":[15],"aggressive":[16],"lossy":[17],"compression":[18,36,171],"risks":[19],"degrading":[20],"the":[21,108,123],"structural":[22,115],"cues":[23],"(edges,":[24],"boundaries,":[25],"semantic":[27],"layouts)":[28],"which":[30],"models":[32],"depend.":[33],"Generative":[34],"image":[35],"can":[37],"synthesize":[38],"perceptually":[39],"plausible":[40],"details":[41,121],"at":[42,107],"low":[43],"bitrates,":[44],"yet":[45],"existing":[46],"methods":[47],"separate":[48],"structure-critical":[49,89],"from":[50,91,122],"synthesizable":[51],"information":[52,90],"either":[53],"statically":[54],"or":[55],"implicitly,":[56],"leaving":[57],"retrieval-relevant":[58],"structure":[59,166],"unprotected.":[60],"We":[61],"introduce":[62],"Uncertainty-Gated":[63],"Variational":[64],"Inference":[65],"(UG-VI),":[66],"a":[67,80,169],"framework":[68],"that":[69,84,149],"embeds":[70],"deterministic":[71],"gating":[72],"into":[73],"hierarchical":[74],"VAEs.":[75],"Its":[76],"ELBO":[77],"derivation":[78],"yields":[79],"decoupling":[81],"KL":[82],"term":[83],"explicitly":[85],"penalizes":[86],"withholding":[87],"predictable,":[88],"transmission.":[92],"The":[93],"resulting":[94],"codec,":[95],"Uncertainty-gated":[96],"Structural":[97],"Compression":[98],"(USC),":[99],"ranks":[100],"latent":[101],"elements":[102],"by":[103],"hyperprior-predicted":[104],"uncertainty":[105],"(available":[106],"decoder":[109],"without":[110],"side":[111],"information),":[112],"transmitting":[113],"low-uncertainty":[114],"latents":[116],"synthesizing":[118],"high-uncertainty":[119],"stochastic":[120],"conditional":[124],"prior.":[125],"On":[126],"CLIC2020,":[127],"USC":[128,150],"achieves":[129],"41.38%":[130],"FID":[131],"BD-Rate":[132],"reduction":[133],"over":[134],"MS-ILLM":[135],"while":[136],"maintaining":[137],"distortion":[138],"(PSNR":[139],"BD-Rate:":[140],"\\(-1.13\\%\\)).":[141],"Retrieval-after-compression":[142],"evaluation":[143],"Oxford5k":[145],"RParis6k":[147],"shows":[148],"preserves":[151],"downstream":[152],"accuracy":[154],"(mAP)":[155],"more":[156],"effectively":[157],"than":[158],"both":[159],"traditional":[160],"generative":[162],"baselines,":[163],"validating":[164],"uncertainty-guided":[165],"preservation":[167],"as":[168],"retrieval-aware":[170],"strategy.":[172]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}